INDEX

Explanations

words related to coverings, whether literal or figurative

oai_token-act-pair · gpt-3.5-turbo

the word "blanket" and its variations, indicating discussions about coverage, protection, or metaphorical uses of the term

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ymes

-0.75

ctions

-0.71

 resil

-0.69

Naz

-0.62

tics

-0.62

sych

-0.60

Oro

-0.59

Ķ

-0.59

 admirable

-0.59

module

-0.59

POSITIVE LOGITS

 blanket

1.24

abies

0.86

 COVER

0.84

sheets

0.83

 blankets

0.83

eding

0.80

krit

0.78

wart

0.74

aby

0.73

spread

0.73

Activations Density 0.019%

words related to coverings, whether literal or figurative

the word "blanket" and its variations, indicating discussions about coverage, protection, or metaphorical uses of the term

No Comments

No Known Activations